?
Stochastic saddle-point optimization for the Wasserstein barycenter problem
Optimization Letters. 2022. Vol. 16. No. 7. P. 2145–2175.
We consider the population Wasserstein barycenter problem for random probability measures supported on a finite set of points and generated by an online stream of data. This leads to a complicated stochastic optimization problem where the objective is given as an expectation of a function given as a solution to a random optimization problem. We employ the structure of the problem and obtain a convex–concave stochastic saddle-point reformulation of this problem. In the setting when the distribution of random probability measures is discrete, we propose a stochastic optimization algorithm and estimate its complexity. The second result, based on kernel methods, extends the previous one to the arbitrary distribution of random probability measures. Moreover, this new algorithm has a total complexity better than the Stochastic Approximation approach combined with the Sinkhorn algorithm in many cases. We also illustrate our developments by a series of numerical experiments.
Фирсанова В. И., Journal of Mathematical Sciences 2024 Vol. 285 No. 1 P. 112–125
Text-to-image models use user-generated prompts to produce images. Such text-to-image models as DALL-E 2, Imagen, Stable Diffusion, and Midjourney can generate photorealistic or similar to human-drawn images. Apart from imitating human art, large text-to-image models have learned to produce combinations of pixels reminiscent of captions in natural languages. For example, a generated image might contain ...
Added: September 9, 2026
Фирсанова В. И., Человек: образ и сущность. Гуманитарные аспекты 2025 Vol. 2 No. 62 P. 203–214
Abstract. The paper highlights prompt engineering in academic setting to reduce plagiarism and increase students' interest. The research problem is the lack of a unified methodology for using artificial intelligence in education. The paper aims to create a generative artificial intelligence user interface, the Virtual Teaching Assistant. Teachers were interviewed, the first collection of presets ...
Added: September 9, 2026
Вохминцев И. В., Вестник международных организаций: образование, наука, новая экономика 2026 Т. 21 № 2
The EAEU and the CSTO are Russia’s principal regional international organisations. Understanding, assessing, and analysing the foreign-policy positions of the countries that belong to them is a matter of the state’s national interests. This determines the purpose of the study: to identify the level and the form of cohesion in the voting of EAEU and ...
Added: September 7, 2026
Alshanskaia E., Portnova G., Liaukovich K. et al., Frontiers in Neuroscience 2024 Vol. 18
Added: September 7, 2026
Зуенко Д. О., Trofimova E., Хайдарова И., IEEE Access 2026 Vol. 14 P. 121339–121357
Oil spill segmentation in Synthetic Aperture Radar (SAR) images is limited by noisy annotations in publicly available datasets and by architectural choices that interact with label quality in opposing directions. First, we introduce a manually refined version of the Deep-SAR Oil Spill (SOS) dataset, in which 36.25% of masks are corrected for false positives, missed ...
Added: September 7, 2026
Kelbert M., Statistics 2026 Vol. 60
We present variational representations for the weighted divergencies
and exponential error function, and discuss implications for the
statistical inference and entropic optimal transport. ...
Added: September 7, 2026
Неверов В. Д., Красавин А. В., Vagov A. et al., Physical Review B: Condensed Matter and Materials Physics 2026 Vol. 113 P. 1–6
We develop a neural network approach to solve the self-consistent Bogoliubov-de Gennes equations in strongly disordered s-wave superconductors. The method accurately reproduces inhomogeneous gap distributions and generalizes to system sizes far larger than those used in training. It reduces computational scaling from O(N6 ) to O(N2), enabling quantitative analysis of percolation phenomena and the superconductor-insulator ...
Added: September 5, 2026
Sheshukova M., Durmus A., Khusainov M. et al., Statistics 2026 P. 1–25
In this paper, we consider the problem of Gaussian approximation for the online linear regression task. We derive the corresponding rates for the setting of a constant stepsize and study the explicit dependence of the convergence rate on the problem dimension d and quantities related to the design matrix. When the number of iterations n is known in advance, ...
Added: September 4, 2026
Proceedings of Machine Learning Research , 2026.
Added: September 4, 2026
Khodadoust J., Kulikova S., Khodadoust F., Biomedical Signal Processing and Control 2027 Vol. 129 P. 111284–111284
Acute ischemic stroke (AIS) analysis from two-dimensional (2D) clinical imaging is hindered by uncontrolled slice tilt and geometric inconsistencies that violate the assumptions of pose-agnostic deep learning (DL) models. This paper proposes a unified geometry-aware, frequency-domain framework for tilted slice localization and ischemic stroke segmentation that explicitly decouples pose estimation from lesion analysis. The method ...
Added: September 2, 2026
IEEE, 2026.
On behalf of the Organizing Committee, it is my great pleasure to extend a warm
welcome to all participants of the Fourth International IEEE Conference on
Distributed Computing and High-Performance Computing (DCHPC 2026), held
in Tehran from May 10–11, 2026. This conference is jointly organized by the
School of Computer Science at the Institute for Research in Fundamental
Sciences (IPM) ...
Added: September 2, 2026
S.M. Avdoshin, Patrushev K. A., Proceedings of the Institute for System Programming of the RAS 2026 Vol. 38 No. 4-2 P. 245–256
The cardinality-constrained Markowitz problem is NP-hard and traditionally solved with commercial MIQP solvers. Following the 2022 export restrictions that rendered both commercial MIQP software and cloud quantum platforms (IBM Quantum, D-Wave Leap) inaccessible from the Russian Federation, practitioners require open-source alternatives. This paper systematically compares three solver families for the discrete mean-variance problem: two open-source ...
Added: August 27, 2026
Zaikin A., Vlasenko D., Zakharov D. et al., Diagnostics 2026 Vol. 16 No. 17 P. 1–15
Background/Objectives: Synolitic graphs (SGs) were developed for task-based fMRI, where
edge weights encode the discriminative power of pairwise regional features; whether similar
information can be recovered from resting-state data was untested. We benchmarked
SGs for autism spectrum disorder (ASD) classification using the multisite ABIDE-I dataset
(871 subjects: 403 subjects with ASD, 468 typical controls; 17 sites; CC200 atlas). Methods:
Using ...
Added: August 27, 2026
Тула: Тульский государственный педагогический университет им. Л.Н. Толстого, 2025.
Сборник содержит материалы, представленные на XXIV Международной конференции «Алгебра, теория чисел, дискретная геометрия и многомасштабное моделирование: современные проблемы, приложения и проблемы истории», посвящённой 110-летию со дня рождения академика Юрия Владимировича Линника и 110-летию со дня рождения профессора Андрея Борисовича Шидловского и 80-летию со дня рождения профессора Геннадия Ивановича Архипова. Материалы конференции будут полезны научным работникам, ...
Added: August 27, 2026
Eduard Sopin, Nazarin A., Begishev V. et al., IEEE Transactions on Vehicular Technology 2026 Vol. 75 No. 6 P. 10995–11007
Aimed at rate-greedy applications having extreme requirements for the data rate at the air interface, 5G New Radio (NR) systems may experience problems when the number of user equipment (UE) in the coverage of the cell increases due to limited capacity of the physical downlink control channel (PDCCH).The aim of this study is to explore ...
Added: August 26, 2026
Джонов А. Т., Avdoshin S. M., Информационные технологии 2026 Т. 32 № 8 С. 421–427
This systematic review presents an analysis of the "Vibe Coding" methodology — a contemporary approach to the iterative software development process using Large Language Models (LLMs). Code generation tools are transforming software development by enabling programmers to formulate tasks and describe the desired behavior of software in natural language, while LLMs generate source code corresponding ...
Added: August 25, 2026
Kornilov N., Gasnikov A., Dvurechensky P. et al., Computational Management Science 2023 Article 37
We present two easy-to-implement gradient-free/zeroth-order methods to optimize a stochastic non-smooth function accessible only via a black-box. The methods are built upon efficient first-order methods in the heavy-tailed case, i.e., when the gradi- ent noise has infinite variance but bounded (1 + 𝜅)-th moment for some 𝜅 ∈ (0, 1]. The first algorithm is based ...
Added: February 7, 2025
Gladin E., Gasnikov A., Ermakova E., Mathematical notes 2022 Vol. 112 No. 1 P. 183–190
The paper deals with a general problem of convex stochastic optimization in a space of small dimension (for example, 100 variables). It is known that for deterministic problems of convex optimization in small dimensions, the methods of centers of gravity type (for example, Vaidya’s method) provide the best convergence. For stochastic optimization problems, the question ...
Added: November 29, 2024
Gladin E., Зайнуллина К. Э., Компьютерные исследования и моделирование 2021 Т. 13 № 6 С. 1137–1147
The article considers minimization of the expectation of convex function. Problems of this type often arise in machine learning and a variety of other applications. In practice, stochastic gradient descent (SGD) and similar procedures are usually used to solve such problems. We propose to use the ellipsoid method with mini-batching, which converges linearly and can ...
Added: November 29, 2024
Alashqar B., Gasnikov A., Dvinskikh D. et al., Computational Mathematics and Mathematical Physics 2023 Vol. 63 P. 1600–1653
This paper studies non-smooth problems of convex stochastic optimization. Using the smoothing technique based on the replacement of the function value at the considered point by the averaged function value over a ball (in l1-norm or l2-norm) of a small radius centered at this point, and then the original problem is reduced to a smooth problem (whose ...
Added: March 27, 2024
Kornilov N., Shamir O., Lobanov A. et al., , in: Advances in Neural Information Processing Systems 36 (NeurIPS 2023).: Curran Associates, Inc., 2023. P. 64083–64102.
Added: March 26, 2024
Schechtman S., Tiapkin D., Muehlebach M. et al., , in: Proceedings of Machine Learning Research: Volume 195: The Thirty Sixth Annual Conference on Learning Theory, 12-15 July 2023, Bangalore, IndiaVol. 195: The Thirty Sixth Annual Conference on Learning Theory, 12-15 July 2023, Bangalore, India.: PMLR, 2023. P. 1228–1258.
We consider the problem of minimizing a non-convex function over a smooth manifold M. We propose a novel algorithm, the Orthogonal Directions Constrained Gradient Method (ODCGM), which only requires computing a projection onto a vector space. ODCGM is infeasible but the iterates are constantly pulled towards the manifold, ensuring the convergence of ODCGM towards M. ...
Added: December 1, 2023
Beznosikov A., Novitskii V., Gasnikov A., , in: Mathematical Optimization Theory and Operations Research: 20th International Conference, MOTOR 2021, Irkutsk, Russia, July 5–10, 2021, Proceedings.: Cham: Springer, 2021. Ch. 261179 P. 144–158.
In this paper, we analyze gradient-free methods with one-point feedback for stochastic saddle point problems min xmax yφ(x, y). For non-smooth and smooth cases, we present an analysis in a general geometric setup with the arbitrary Bregman divergence. For problems with higher order smoothness, the analysis is carried out only in the Euclidean case. The estimates we have obtained repeat the best currently known estimates of gradient-free ...
Added: October 30, 2022
Dvinskikh D., Tominin V., Tominin I. et al., , in: Mathematical Optimization Theory and Operations Research, 21st International Conference, MOTOR 2022, Petrozavodsk, Russia, July 2–6, 2022, ProceedingsVol. 13367.: Springer, 2022. Ch. 279899 P. 18–33.
Added: October 28, 2022